Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 883 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.4301. Min Act: -0.1700

Data Index: 65538 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3676. Min Act: -0.1700

Data Index: 97136 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.4301. Min Act: -0.1700

Data Index: 751530 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.4301. Min Act: -0.1700

Data Index: 1130572 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3988. Min Act: -0.1700

Data Index: 496728 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3363. Min Act: -0.1700

Data Index: 477981 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3988. Min Act: -0.1700

Data Index: 730366 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.4926. Min Act: -0.1700

Data Index: 69620 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.4301. Min Act: -0.1700

Data Index: 1123215 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3676. Min Act: -0.1700

Data Index: 599469 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3676. Min Act: -0.1700

Data Index: 721551 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3676. Min Act: -0.1700

Data Index: 158473 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.4301. Min Act: -0.1700

Data Index: 526535 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3676. Min Act: -0.1700

Data Index: 660858 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3363. Min Act: -0.1700

Data Index: 985033 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3676. Min Act: -0.1700

Data Index: 509387 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3676. Min Act: -0.1700

Data Index: 688100 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3363. Min Act: -0.1700

Data Index: 1008599 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3051. Min Act: -0.1700

Data Index: 624846 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 5.4926. Min Range: -5.4926

Max Act: 5.3363. Min Act: -0.1700

Data Index: 312212 (C4 (Web Text))

Max Activating Token Index: 329